Google trends keywords used to train the model.

As of 2022, COVID-19, first reported in Wuhan, China, in November 2019, has become a worldwide epidemic, causing numerous infections and casualties and enormous social and economic damage. To mitigate its impact, various COVID-19 prediction studies have emerged, most of them using mathematical models and artificial intelligence for prediction. However, the problem with these models is that their prediction accuracy is considerably reduced when the duration of the COVID-19 outbreak is short. In this paper, we propose a new prediction method combining Word2Vec and the existing long short-term memory and Seq2Seq + Attention model. We compare the prediction error of the existing and proposed models with the COVID-19 prediction results reported from five US states: California, Texas, Florida, New York, and Illinois. The results of the experiment show that the proposed model combining Word2Vec and the existing long short-term memory and Seq2Seq + Attention achieves better prediction results and lower errors than the existing long short-term memory and Seq2Seq + Attention models. In experiments, the Pearson correlation coefficient increased by 0.05 to 0.21 and the RMSE decreased by 0.03 to 0.08 compared to the existing method.